Optical coherence tomography and computer-aided diagnosis of a murine model of chronic kidney disease

In vivo imaging of renal microvasculature in a murine ischemia-reperfusion injury model using optical coherence tomography angiography

Optical coherence tomography angiography (OCTA) provides three-dimensional structural and semiquantitative imaging of microvasculature in vivo. We developed an OCTA imaging protocol for a murine kidney ischemia-reperfusion injury (IRI) model to investigate the correlation between renal microvascular changes and ischemic damage. Mice were divided into mild and moderate IRI groups according to the duration of ischemia (10 and 35 mins, respectively). Each animal was imaged at baseline; during ischemia; and at 1, 15, 30, 45, and 60 mins after ischemia. Amplitude decorrelation OCTA images were constructed with 1.5-, 3.0-, and 5.8-ms interscan times, to calculate the semiquantitative flow index in the superficial (50-70 μm) and the deep (220-340 μm) capillaries of the renal cortex. The mild IRI group showed no significant flow index change in both the superfial and the deep layers. The moderate IRI group showed a significantly decreased flow index from 15 and 45 mins in the superficial and deep layers, respectively. Seven weeks after IRI induction, the moderate IRI group showed lower kidney function and higher collagen deposition than the mild IRI group. OCTA imaging of the murine IRI model revealed changes in superficial blood flow after ischemic injury. A more pronounced decrease in superficial blood flow than in deep blood flow was associated with sustained dysfunction after IRI. Further investigation on post-IRI renal microvascular response using OCTA may improve our understanding of the relationship between the degree of ischemic insult and kidney function.

Feasibility of the soft attention-based models for automatic segmentation of OCT kidney images

Clinically, optical coherence tomography (OCT) has been utilized to obtain the images of the kidney's proximal convoluted tubules (PCTs), which can be used to quantify the morphometric parameters such as tubular density and diameter. Such parameters are useful for evaluating the status of the donor kidney for transplant. Quantifying PCTs from OCT images by human readers is a time-consuming and tedious process. Despite the fact that conventional deep learning models such as conventional neural networks (CNNs) have achieved great success in the automatic segmentation of kidney OCT images, gaps remain regarding the segmentation accuracy and reliability. Attention-based deep learning model has benefits over regular CNNs as it is intended to focus on the relevant part of the image and extract features for those regions. This paper aims at developing an Attention-based UNET model for automatic image analysis, pattern recognition, and segmentation of kidney OCT images. We evaluated five methods including the Residual-Attention-UNET, Attention-UNET, standard UNET, Residual UNET, and fully convolutional neural network using 14403 OCT images from 169 transplant kidneys for training and testing. Our results show that Residual-Attention-UNET outperformed the other four methods in segmentation by showing the highest values of all the six metrics including dice score (0.81 ± 0.01), intersection over union (IOU, 0.83 ± 0.02), specificity (0.84 ± 0.02), recall (0.82 ± 0.03), precision (0.81 ± 0.01), and accuracy (0.98 ± 0.08). Our results also show that the performance of the Residual-Attention-UNET is equivalent to the human manual segmentation (dice score = 0.84 ± 0.05). Residual-Attention-UNET and Attention-UNET also demonstrated good performance when trained on a small dataset (3456 images) whereas the performance of the other three methods dropped dramatically. In conclusion, our results suggested that the soft Attention-based models and specifically Residual-Attention-UNET are powerful and reliable methods for tubule lumen identification and segmentation and can help clinical evaluation of transplant kidney viability as fast and accurate as possible.

Application of multiparametric MR imaging to predict the diversification of renal function in miR29a-mediated diabetic nephropathy

Diabetic nephropathy (DN) is one of the major leading cause of kidney failure. To identify the progression of chronic kidney disease (CKD), renal function/fibrosis is playing a crucial role. Unfortunately, lack of sensitivities/specificities of available clinical biomarkers are key major issues for practical healthcare applications to identify the renal functions/fibrosis in the early stage of DN. Thus, there is an emerging approach such as therapeutic or diagnostic are highly desired to conquer the CKD at earlier stages. Herein, we applied and examined the application of dynamic contrast enhanced magnetic resonance imaging (DCE-MRI) and diffusion weighted imaging (DWI) to identify the progression of fibrosis between wild type (WT) and miR29a transgenic (Tg) mice during streptozotocin (STZ)-induced diabetes. Further, we also validate the potential renoprotective role of miR29a to maintain the renal perfusion, volume, and function. In addition, Ktrans values of DCE-MRI and apparent diffusion coefficient (ADC) of DWI could significantly reflect the level of fibrosis between WT and Tg mice at identical conditions. As a result, we strongly believed that the present non-invasive MR imaging platforms have potential to serveas an important tool in research and clinical imaging for renal fibrosis in diabetes, and that microenvironmental changes could be identified by MR imaging acquisition prior to histological biopsy and diabetic podocyte dysfunction.

Fully automated analysis of OCT imaging of human kidneys for prediction of post-transplant function

Current measures for assessing the viability of donor kidneys are lacking. Optical coherence tomography (OCT) can image subsurface tissue morphology to supplement current measures and potentially improve prediction of post-transplant function. OCT imaging was performed on donor kidneys before and immediately after implantation during 169 human kidney transplant surgeries. A system for automated image analysis was developed to measure structural parameters of the kidney's proximal convoluted tubules (PCTs) visualized in the OCT images. The association of these structural parameters with post-transplant function was investigated. This study included kidneys from live and deceased donors. 88 deceased donor kidneys in this study were stored by static cold storage (SCS) and an additional 15 were preserved by hypothermic machine perfusion (HMP). A subset of both SCS and HMP deceased donor kidneys were classified as expanded criteria donor (ECD) kidneys, with elevated risk of poor post-transplant function. Post-transplant function was characterized as either immediate graft function (IGF) or delayed graft function (DGF). In ECD kidneys stored by SCS, increased PCT lumen diameter was found to predict DGF both prior to implantation and following reperfusion. In SCD kidneys preserved by HMP, reduced distance between adjacent lumen following reperfusion was found to predict DGF. Results suggest that OCT measurements may be useful for predicting post-transplant function in ECD kidneys and kidneys stored by HMP. OCT analysis of donor kidneys may aid in allocation of kidneys to expand the donor pool as well as help predict post-transplant function in transplanted kidneys to inform post-operative care.

Depth-resolved mapping of muscular bundles in myocardium pulmonary junction using optical coherence tomography

Atrial fibrillation (AF) is the most common cardiac arrhythmia and has high patient morbidity. One of the root causes of AF is initiating triggers from atrial myocardium extending into the pulmonary veins. Visualizing the muscular bundles of myocardial extension is essential to guide the catheter radio-frequency ablation and confirm the curative tissue necrosis thereafter. We applied optical coherence tomography (OCT) for direct visualization of cardial muscle extension in myocardium pulmonary junction. Two perspectives (cross-sectional and en face images) are presented for imaging myocardial extensions. The results demonstrated that cross-sectional images can quickly locate the myocardium pulmonary junction. And en face images provide depth-resolved arrangement information of muscular bundles in the myocardium pulmonary junction. The results indicated that OCT could potentially be used to guide catheter radio-frequency ablation for treatment of AF.